Real-estate client management method and system

Abstract

In one aspect, a computer-implemented method of real-estate entity segmentation includes classifying a set of property attributes of one or more real-estate entities using a logistic regression method. The real-estate entities are taken from a realtor's client contact list. A probability of a real-estate transaction occurring for each of the one or more real-estate entities is determined based on the set of property attributes of the one or more real-estate entities. A step includes identifying that a real-estate entity is more likely being sold or listed when the probability of a real-estate transaction occurring is above a specified threshold. The real-estate entity that is more likely being sold or listed is included in a clustering data set. A step includes implementing a fuzzy-C means clustering algorithm on all or a portion of the clustering data set to obtain a cluster center for a specified set of the property attributes. The real-estate entity is classified to a real-estate segment based on a location of the real entity in the cluster. The real-estate entity is added to the real-estate segment.

What is claimed as new and desired to be protected by Letters Patent of the United States is: 
     
         1 . A method of real-estate client management comprising:
 receiving a realtor's client contact list;   matching an client entity of the client contact list with a real-estate entity, wherein the real-estate entity comprises a real-estate property owned or leased by the client entity;   obtaining a real-estate entity attribute database from a real-estate entity attribute aggregator;   determining a real-estate entity attribute from the real-estate entity attribute database;   assigning the real-estate entity attribute to the client entity; and   based on the real-estate entity attribute, assigning a predicted future action to the client entity with respect to the real-estate entity.   
     
     
         2 . The method of  claim 1  further comprising:
 obtaining a client-entity attribute database from a client-entity attribute aggregator; 
 determining a client-entity attribute from the client-entity attribute database; and 
 based on the client-entity attribute or the real-estate entity attribute, assigning the predicted future action to the client entity with respect to the real-estate entity. 
 
     
     
         3 . The method of  claim 2 , wherein the future action comprises a prediction that the client entity will sell the real-estate entity. 
     
     
         4 . The method of  claim 3 , wherein the future action comprises a prediction that the client entity will sell the real-estate entity and purchase a smaller-sized real-estate entity. 
     
     
         5 . The method of  claim 3 , wherein the future action comprises a prediction that the client entity will sell the real-estate entity and purchase a larger-sized real-estate entity. 
     
     
         6 . The method of  claim 2 , wherein the client-entity attribute comprises a demographic attribute of the owner of the real-estate entity. 
     
     
         7 . The method of  claim 2 , wherein the real-estate entity attribute comprises a size of a home. 
     
     
         8 . The method of  claim 2  further comprising:
 automatically generating a digital advertisement targeted to the future action of the client entity. 
 
     
     
         9 . The method of  claim 8  further comprising:
 detecting a change in the real-estate entity attribute or the client-entity attribute; 
 automatically modifying the future action of the client entity; and 
 automatically modifying the digital advertisement targeted to the modified future action of the entity. 
 
     
     
         10 . A computerized system comprising:
 a processor configured to execute instructions;   a memory containing instructions when executed on the processor, causes the processor to perform operations that:
 receive a realtor's client contact list; 
 match an client entity of the client contact list with a real-estate entity, wherein the real-estate entity comprises a real-estate property owned or leased by the client entity; 
 obtain a real-estate entity attribute database from a real-estate entity attribute aggregator, 
 determine a real-estate entity attribute from the real-estate entity attribute database; 
 assign the real-estate entity attribute to the client entity; 
 obtain a client-entity attribute database from a client-entity attribute aggregator; 
 determine a client-entity attribute from the client-entity attribute database; and 
 based on the client-entity attribute or the real-estate entity attribute, assign the predicted future action to the client entity with respect to the real-estate entity. 
   
     
     
         11 . A computer-implemented method of real-estate entity segmentation comprising:
 classifying a set of property attributes of one or more real-estate entities using a logistic regression method, wherein the real-estate entities are taken from a realtor's client contact list;   determining a probability of a real-estate transaction occurring for each of the one or more real-estate entities based on the set of property attributes of the one or more real-estate entities;   identifying that a real-estate entity is more likely being sold or listed when the probability of a real-estate transaction occurring is above a specified threshold; including the real-estate entity that is more likely being sold or listed in a clustering data set;   implementing a fuzzy-C means clustering algorithm on all or a portion of the clustering data set to obtain a cluster center for a specified set of the property attributes;   classifying the real-estate entity to a real-estate segment based on a location of the real entity in the cluster;   adding the real-estate entity to the real-estate segmentation.   
     
     
         12 . The computer-implemented method of  claim 11  further comprising:
 scaling the one or more real-estate entities within a tract. 
 
     
     
         13 . The computer-implemented method of  claim 12  further comprising:
 calculating a kurtosis value, a skewness value, a variance value, a median value, a tract size value and an event-rate value for the tract. 
 
     
     
         14 . The computer-implemented method of  claim 13 , wherein a scaling-operation comprises a scaling equation, wherein the scaling equation comprises: (prob−min(prob))/(max(prob)−min(prob)), and wherein the scaling equation scales a set of real-estate entities within the same tract. 
     
     
         15 . The computer-implemented method of  claim 14 , wherein the specified threshold comprises between a twenty (20) percentile to eighty (80) percentile of probability of being sold or listed. 
     
     
         16 . The computer-implemented method of  claim 15 , wherein probability threshold is determined based on an F-score. 
     
     
         17 . The computer-implemented method of  claim 16 , wherein further comprises: building a fuzzy-c means;
 setting a cluster number to three (3);   obtaining a cluster center; and   segmenting a set of properties by a majority vote.   
     
     
         18 . The computer-implemented method of  claim 11 , wherein the real-estate segment comprises a move-up segment, a move-down segment or a not moving segment.